mcp-read-website-fast
by just-every·★ 146·Score 48
A fast, token-efficient MCP server that converts websites to clean Markdown for AI agents.
Overview
This MCP server provides fast web content extraction by fetching pages locally, stripping noise, and converting content to clean Markdown while preserving links. It's designed for Claude Code, IDEs, and LLM pipelines with minimal token footprint. The package uses Mozilla Readability (same as Firefox Reader View) for content extraction and Turndown for HTML to Markdown conversion.
Try asking AI
After installing, here are 5 things you can ask your AI assistant:
When to choose this
Choose this when you need fast, token-efficient web scraping for AI agents, especially when working with Claude Code or IDEs and need to convert websites to clean markdown.
When NOT to choose this
Don't choose this if you need to interact with JavaScript-heavy websites that require execution to render content, or if you need advanced authentication mechanisms beyond custom user agents.
Tools this server exposes
1 tool extracted from the READMEread_websiteurl: string, pages?: numberFetches a webpage and converts it to clean markdown
Comparable tools
Installation
Installation
Claude Code
claude mcp add read-website-fast -s user -- npx -y @just-every/mcp-read-website-fastVS Code
code --add-mcp '{"name":"read-website-fast","command":"npx","args":["-y","@just-every/mcp-read-website-fast"]}'Raw JSON (works in any MCP client)
{
"mcpServers": {
"read-website-fast": {
"command": "npx",
"args": ["-y", "@just-every/mcp-read-website-fast"]
}
}
}FAQ
- How does this server handle websites with JavaScript?
- This server doesn't execute JavaScript. It works best with static content. Sites requiring JavaScript may not be fully scraped.
- Can I customize the crawling behavior?
- Yes, you can configure concurrency, depth, user agent, timeout, and other parameters via CLI options or direct function calls.
Compare mcp-read-website-fast with
Last updated · Auto-generated from public README + GitHub signals.